Search Results for author: Akshay Balsubramani

Found 19 papers, 7 papers with code

p-value peeking and estimating extrema

no code implementations2 Nov 2020 Akshay Balsubramani

A pervasive issue in statistical hypothesis testing is that the reported $p$-values are biased downward by data "peeking" -- the practice of reporting only progressively extreme values of the test statistic as more data samples are collected.

Two-sample testing

Sharp finite-sample concentration of independent variables

no code implementations30 Aug 2020 Akshay Balsubramani

We show an extension of Sanov's theorem on large deviations, controlling the tail probabilities of i. i. d.

Learning transport cost from subset correspondence

no code implementations ICLR 2020 Ruishan Liu, Akshay Balsubramani, James Zou

Optimal transport (OT) is a principled approach to align datasets, but a key challenge in applying OT is that we need to specify a transport cost function that accurately captures how the two datasets are related.

An adaptive nearest neighbor rule for classification

1 code implementation NeurIPS 2019 Akshay Balsubramani, Sanjoy Dasgupta, Yoav Freund, Shay Moran

We introduce a variant of the $k$-nearest neighbor classifier in which $k$ is chosen adaptively for each query, rather than supplied as a parameter.

Classification General Classification +1

Linking Generative Adversarial Learning and Binary Classification

no code implementations5 Sep 2017 Akshay Balsubramani

In this note, we point out a basic link between generative adversarial (GA) training and binary classification -- any powerful discriminator essentially computes an (f-)divergence between real and generated samples.

Classification General Classification

Optimal Binary Autoencoding with Pairwise Correlations

no code implementations7 Nov 2016 Akshay Balsubramani

We formulate learning of a binary autoencoder as a biconvex optimization problem which learns from the pairwise correlations between encoded and decoded bits.

Muffled Semi-Supervised Learning

1 code implementation28 May 2016 Akshay Balsubramani, Yoav Freund

We explore a novel approach to semi-supervised learning.

Learning to Abstain from Binary Prediction

no code implementations25 Feb 2016 Akshay Balsubramani

A binary classifier capable of abstaining from making a label prediction has two goals in tension: minimizing errors, and avoiding abstaining unnecessarily often.

The Utility of Abstaining in Binary Classification

no code implementations26 Dec 2015 Akshay Balsubramani

We explore the problem of binary classification in machine learning, with a twist - the classifier is allowed to abstain on any datum, professing ignorance about the true class label without committing to any prediction.

Active Learning Classification +2

Optimal Binary Classifier Aggregation for General Losses

1 code implementation NeurIPS 2016 Akshay Balsubramani, Yoav Freund

We address the problem of aggregating an ensemble of predictors with known loss bounds in a semi-supervised binary classification setting, to minimize prediction loss incurred on the unlabeled data.

General Classification

PAC-Bayes Iterated Logarithm Bounds for Martingale Mixtures

no code implementations22 Jun 2015 Akshay Balsubramani

We give tight concentration bounds for mixtures of martingales that are simultaneously uniform over (a) mixture distributions, in a PAC-Bayes sense; and (b) all finite times.

Scalable Semi-Supervised Aggregation of Classifiers

1 code implementation NeurIPS 2015 Akshay Balsubramani, Yoav Freund

We present and empirically evaluate an efficient algorithm that learns to aggregate the predictions of an ensemble of binary classifiers.

Sequential Nonparametric Testing with the Law of the Iterated Logarithm

no code implementations10 Jun 2015 Akshay Balsubramani, Aaditya Ramdas

It is novel in several ways: (a) it takes linear time and constant space to compute on the fly, (b) it has the same power guarantee as a non-sequential version of the test with the same computational constraints up to a small factor, and (c) it accesses only as many samples as are required - its stopping time adapts to the unknown difficulty of the problem.

Two-sample testing

Optimally Combining Classifiers Using Unlabeled Data

1 code implementation5 Mar 2015 Akshay Balsubramani, Yoav Freund

We develop a worst-case analysis of aggregation of classifier ensembles for binary classification.

General Classification

PAC-Bayes with Minimax for Confidence-Rated Transduction

no code implementations15 Jan 2015 Akshay Balsubramani, Yoav Freund

We consider using an ensemble of binary classifiers for transductive prediction, when unlabeled test data are known in advance.

The Fast Convergence of Incremental PCA

no code implementations NeurIPS 2013 Akshay Balsubramani, Sanjoy Dasgupta, Yoav Freund

We consider a situation in which we see samples in $\mathbb{R}^d$ drawn i. i. d.

Sharp Finite-Time Iterated-Logarithm Martingale Concentration

no code implementations12 May 2014 Akshay Balsubramani

We give concentration bounds for martingales that are uniform over finite times and extend classical Hoeffding and Bernstein inequalities.

Cannot find the paper you are looking for? You can Submit a new open access paper.